README.md

metadata

title: AgriPredict
emoji: 🌾
colorFrom: green
colorTo: yellow
sdk: streamlit
sdk_version: 1.49.1
app_file: streamlit_app.py
pinned: false

AgriPredict (Refactor)

AgriPredict is a refactored, modular, and production-ready version of the original Streamlit-based price forecasting dashboard.
This version focuses on better structure, maintainability, and performance.

---

📁 Project Structure

src/agri_predict/
│
├── config.py        # Environment variables, MongoDB client setup
├── constants.py     # Shared constant mappings (states, markets, crops etc.)
├── features.py      # Feature engineering functions
├── data.py          # Data access, scraping, cleaning, preprocessing
├── models.py        # Model training, forecasting, grid search
├── plotting.py      # Plot utilities, downloads
└── utils.py         # Authentication + general helpers

streamlit_app.py     # Streamlit UI entrypoint
requirements.txt     # Python dependencies

---

▶️ Run Locally

1. Create and activate a virtual environment:

python -m venv .venv
source .venv/bin/activate

2. Install dependencies:

pip install -r requirements.txt

3. Set up environment variables

Create a .env file in the project root:

MONGO_URI=your_mongo_connection_string

4. Start the Streamlit app:

streamlit run streamlit_app.py

---

🚀 Deploy on Hugging Face Spaces

This README already includes the required HF metadata block at the top.
Hugging Face Spaces will automatically run:

streamlit run streamlit_app.py

No additional configuration is needed.

---